Loading...
Loading...
Found 6,717 Skills
Rules for handing work to subagents instead of doing it on the main thread. Use when deciding whether to delegate a search, a bulk edit, a documentation lookup or a verification; when writing a delegation prompt; when choosing a model tier; when escalating after a failure; when running agents in parallel; or when a delegated result comes back and you are about to believe it. Covers hard delegation thresholds, the three mandatory prompt elements, the reporting contract, anti-anchoring, parallel-write safety, and why not to ask the user to switch models mid-conversation.
Multi-agent shared blackboard: The current directory is .yomi/boards/<feature>.md, one board per feature, allowing parallel agents/subagents under the same feature to see each other's tasks, progress, and findings. Use when multi-agent collaboration requires peer visibility, sharing progress/findings, wanting to know what peers are doing before starting work, or when terms like "blackboard / board / peer progress" are mentioned. Task assignment/sign-off/state machine/acceptance are handled via task-tickets, not blackboard.
One-time bootstrap of a persistent memory + self-evolution system for an agent workspace. Use when setting up memory for a new agent or workspace, or configuring dream/janitor crons.
Prepara a configuração .brandfy, a árvore de artefatos e as instruções do agente. Use ao instalar ou atualizar o Brandfy em um projeto.
Menulis prosa untuk pengguna coding agent dalam bahasa Indonesia yang alami, dengan pilihan ragam netral atau gaya regional seperti Jakarta, Jaksel, Bandung, Medan, Makassar, Surabaya, Semarang, Yogyakarta, Jawa alus, Banyumasan/Ngapak, dan Kebumen. Gunakan saat pengguna berbahasa Indonesia, meminta balasan Indonesia, atau memilih logat/gaya daerah; jangan terapkan pada kode dan artefak teknis yang harus tetap persis.
Build Celigo MCP server resources -- endpoints that expose Tools and builder-mode APIs to external AI agents and MCP clients. Use when creating MCP servers, linking tools or APIs, or configuring annotations and overrides.
Token-efficient web browsing and web content extraction for AI agents. Use when reading a URL, browsing websites, checking links, extracting static page content, or replacing raw HTML and browser screenshots.
End-to-end work with UiPath Agents of all types: build, integrate with UiPath Products (e.g., Orchestrator, Flow, Maestro), design with UiPath Tools (e.g., Agent Builder/Studio Web), deploy, and configure/validate. Covers Coded Agents (e.g., LangGraph, LlamaIndex, OpenAI Agents) and Low-Code Agents (`agent.json` / Agent Builder). For deterministic Python Coded Functions (`uip function`, `uipath.json` functions map, no agent runtime/LLM)→uipath-functions.
You MUST use this when auditing, improving, restructuring, or maintaining agent instruction files - AGENTS.md, CLAUDE.md and its variants, .claude/rules/, SKILL.md files, or docs linked from them - including reducing always-loaded context cost, finding stale, duplicated, or conflicting instructions, and keeping Claude Code or Codex project memory aligned with the codebase. Not for documentation written for human readers.
Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
Audits the bundled `clerk-cli` skill against the Clerk CLI source tree and proposes or applies updates. Use when the user says "audit the clerk-cli skill", "update the clerk-cli skill", "check clerk-cli against the CLI source", "resync clerk-cli skill", "run audit-clerk-skill", or after Clerk CLI commands, flags, or agent-mode behavior change.